Machine Learned Cellular Phenotypes in Cardiomyopathy Predict Sudden Death

Abstract

Rationale: Susceptibility to ventricular arrhythmias (VT/VF) is difficult to predict in patients with ischemic cardiomyopathy either by clinical tools or by attempting to translate cellular mechanisms to the bedside. Objective: To develop computational phenotypes of patients with ischemic cardiomyopathy, by training then interpreting machine learning (ML) of ventricular monophasic action potentials (MAPs) to reveal phenotypes that predict long-term outcomes. Methods and Results: We recorded 5706 ventricular MAPs in 42 patients with coronary disease (CAD) and left ventricular ejection fraction (LVEF) {less than or equal to}40% during steady-state pacing. Patients were randomly allocated to independent training and testing cohorts in a 70:30 ratio, repeated K=10 fold. Support vector machines (SVM) and convolutional neural networks (CNN) were trained to 2 endpoints: (i) sustained VT/VF or (ii) mortality at 3 years. SVM provided superior classification. For patient-level predictions, we computed personalized MAP scores as the proportion of MAP beats predicting each endpoint. Patient-level predictions in independent test cohorts yielded c-statistics of 0.90 for sustained VT/VF (95% CI: 0.76-1.00) and 0.91 for mortality (95% CI: 0.83-1.00) and were the most significant multivariate predictors. Interpreting trained SVM revealed MAP morphologies that, using in silico modeling, revealed higher L-type calcium current or sodium calcium exchanger as predominant phenotypes for VT/VF. Conclusions: Machine learning of action potential recordings in patients revealed novel phenotypes for long-term outcomes in ischemic cardiomyopathy. Such computational phenotypes provide an approach which may reveal cellular mechanisms for clinical outcomes and could be applied to other conditions.

Identifying Atrial Fibrillation Mechanisms for Personalized Medicine

“…Thus, there is an urgent need to develop a framework that separates these and other AF presentations by their pathophysiology to personalize therapy for each patient. Recent studies applying artificial intelligence (AI) to the ECG and other data types offer such a foundation for computational phenotypes that could guide therapy [ 5 , 6 ].…”

Machine learning techniques for arrhythmic risk stratification: a review of the literature

“…Except for clinical and imaging variables, cellular electrophysiological characteristics have also been studied using ML algorithms to identify ischemic cardiomyopathy patients at risk of SCD [ 29 ]. ML of monophasic action potential recordings in ischemic cardiomyopathy patients revealed novel phenotypes for predicting sustained VT/fventricular fibrillation (VF) [ 29 ].…”

Ventricular voltage‐gated ion channels: Detection, characteristics, mechanisms, and drug safety evaluation

“… 214 With the application of in silico modeling, machine learning could identify cellular electrophysiological phenotypes associated with patients who has certain cardiac diseases and further predict which patients face an elevated risk of ventricular arrhythmias and sudden death. 215 However, information such as comparisons among drugs with similar chemical or affinity profiles is not yet possible incorporated into in an silico model. 216 Thus, newer proarrhythmia risk prediction models could be developed to aid in decision making.…”

“…For example, development of better simulating models to capture the drug response not only in normal humans but also in specific patient populations 214 . With the application of in silico modeling, machine learning could identify cellular electrophysiological phenotypes associated with patients who has certain cardiac diseases and further predict which patients face an elevated risk of ventricular arrhythmias and sudden death 215 . However, information such as comparisons among drugs with similar chemical or affinity profiles is not yet possible incorporated into in an silico model 216 .…”